A Research about the Transmutation Trend of the Silk Road Documentary under Recurrent Neural Network
Miao Zhang, Wei Lu · 2021
The Silk Road documentaries refer to documentaries related to the theme of the Silk Road. Its connotation, scope, and significance have a profound impact on the creation of Chinese documentaries, and become a major documentary genre with a unique style in the history of documentary creation in China. Although the production of documentary about "Silk Road" has achieved remarkable results in both quantity and quality, its development trend is seriously affected by the development iteration of research objects over time and national policies, resulting in the unknown future development of "Silk Road" documentary. Therefore, this paper first reviews and summarizes the theme background and historical development of the Silk Road documentary. Then, a long short-term memory neural network (LSTM) model with gate mechanism and memory unit is used to adaptively model its historical time series data. Finally, the long-term iterative forecasting method is used to gradually introduce the development trend of the number of "Silk Road" documentaries in the next few years. Under the circumstances that the national policy on the Silk Road in the next few years is unknown, this paper could better guide the future development trend of this type of documentary creation in the form of modeling, and provide reference for future scholars in this direction.